Section: New Results

Parsimonious Labeling

Paticipants: Puneet Dokania, Pawan Kumar

In  [22] , we propose a new family of discrete energy minimization problems, which we call parsimonious labeling, that is to use as few labels as possible. This allows us to capture useful cues for important computer vision applications such as stereo correspondence and image denoising. Furthermore, we propose an efficient graph-cuts based algorithm for the parsimonious labeling problem that provides strong theoretical guarantees on the quality of the solution. Using both synthetic and standard real datasets, we show that our algorithm significantly outperforms other graph-cuts based approaches.